A method for detecting abnormal vibration of a rolling mill including a collecting step of collecting vibration data of the rolling mill, a frequency analysis step of generating first analysis data by performing frequency analysis of the vibration data, a principal component analysis step of performing principal component analysis on the first analysis data by using reference data specified in advance on the basis of a normal state as a principal component and thereby generating evaluation data, which is a projection of the first analysis data onto the reference data, and an abnormal vibration detection step of extracting an outlier component from the evaluation data and the first analysis data and detecting an abnormality of the rolling mill from the extracted outlier component.

The invention relates to a roll stand (2) for rolling, in particular cold-rolling, metal products, comprising at least one actuator (16) which can be actuated for actively damping vibrations in the roll stand (2), and at least one supporting roll (10) which is non-adjustable or can be adjusted exclusively via a readjusting device for pass line adjustment (13) of the roll stand (2) for supporting a working roll (5) and/or intermediate roll of the roll stand (2), wherein the supporting roll (10) is guided at the ends via a respective bearing unit (11) on a rack (8) of the roll stand (2). In order to enable an optimal active damping of vibrations in a roll stand (2) of this type with low engineering effort, the invention proposes that the supporting roll (10) is supported on the actuator (16) via at least one bearing unit (11) and that the actuator (16) is supported on a section (17) of the rack (8) either directly or indirectly via at least one component (14) of the readjustment device (13)

The active vibration damping system of a rolling mill comprises a rolling stand and an adjustment system for the bending of the rolling rolls (1, 1) having hydraulic actuators (2\2, 2, 2iv) acting on the chock (20) of the rolling rolls (1, 1) and hydraulic feeding circuits (7, 9, 11, 12) and injectors (8, 8, 8, 8iv), preferably piezoelectric injectors, directly inserted into the chambers (6\6, 6, 6iv) of the hydraulic actuators (2, 2, 2, 2iv) with the advantage of exploiting the dampening effect resulting from the high- pressure oil injection.

Control of third octave vibrations in a mill stand can be achieved using a high-speed piezoelectric assist coupled to a hydraulic gap cylinder to increase the damping of the roll stack. Vertical movements of the roll stack (e.g., the top work roll) can be determined through observation (e.g., measurement) of hydraulic fluid pressure of the hydraulic cylinder or entry tension of the metal strip. After determining vertical movements of the roll stack, a desired change in hydraulic pressure can be determined to overcome, reduce, or prevent third octave vibration. This desired change in hydraulic pressure can be effectuated at high speeds (e.g., at or above approximately 90 hertz) using the piezoelectric assist.

Apparatus to control and adjust the drawing action in a rolling mill provided with rolling stands through which a product passes. A video monitoring system acquires frames of the product; a processing system that processes the frames and defines a normal rolling range within which the product being rolled must be positioned; identifies the position of the product and its geometric characteristics; and identifies a possible variation of the position of the product being rolled over time based on the analysis of the sequence of frames acquired. An automation system is associated with the rolling mill, configured to receive data relating to the position of the product to determine the continuation of the rolling if the product is correctly positioned in the range, or a variation of the rolling parameters if the position of the product being rolled is able to generate a cobble which is outside of the range.

Embodiments of the present disclosure provides a method and device for constructing a multi-dimensional coupled vibration identification model for a roll system of a strip mill, the method comprising: performing preprocessing, signal decomposition, and reconstruction of the multi-dimensional data for the roll system of the strip mill monitored through technical monitoring by multiple sensors during a working process of the strip mill, and performing feature extraction of the reconstructed data using a wavelet packet energy approach; obtaining an initial multi-dimensional coupled vibration feature local identification model for the roll system of the strip mill based on Support Vector Machine (SVM) by using a Gaussian radial basis function as a kernel function of the SVM model; and training the initial multi-dimensional coupled vibration feature local identification model for the roll system of the strip mill using a multi-source heterogeneous information fusion approach based on the feature vector to obtain the multi-dimensional coupled feature identification model for the roll system of the strip mill.

A method of detecting chattering in a cold rolling mill, the method includes: a step of predicting occurrence of chattering during rolling of a material to be rolled, by inputting second multidimensional data to a prediction model, the second multidimensional data having been generated based on condition data corresponding to array data related to the material to be rolled, and the prediction model having been trained with an explanatory variable and an objective variable, the explanatory variable being first multidimensional data generated based on one-dimensional array data representing a past rolling record of rolling of rolled materials by means of a cold rolling mill, and the objective variable being a past record of occurrence of chattering corresponding to the past rolling record.